Metraipolis › archive › dc_0faacd8267bf
Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation — arXiv:2609.37398
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37398
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:23:51.161Z
- SHA-256 of the archived text
fe2dbc8800f82a81e56785b70ce47802e06136b7e2111b5f206c80829a40114c- Stable URL of this page
https://metraipolis.com/documento/dc_0faacd8267bf
How to cite
Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation — arXiv:2609.37398 — arXiv (en), https://arxiv.org/abs/2609.37398 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0faacd8267bf (Metraipolis archive dc_0faacd8267bf, sha256 fe2dbc8800f82a81e56785b70ce47802e06136b7e2111b5f206c80829a40114c)
BibTeX
@misc{dc0faacd8267bf,
title = {Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation — arXiv:2609.37398},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37398},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0faacd8267bf; sha256 fe2dbc8800f82a81e56785b70ce47802e06136b7e2111b5f206c80829a40114c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37398. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning paradigms typically improve behavior without requiring better world predictions. Especially in dexterous manipulation, small execution errors can compound in high-dimensional action spaces, hindering policy improvement and pushing interactions beyond the world model's training distribution. Motivated by this, we propose Direct Experience World-Model Optimization (DEWO), a post-deployment learning paradigm for WAMs that, alongside action imitation, refines world representations through visual experience to better condition action generation. Specifically, it identifies interaction turning points and learns from successful and failed futures to support classifier-free guidance. An additional value head estimates task progress from video representations and activates guidance when progress stalls during inference. Across five DexJoCo tasks, DEWO improves average success across all three WAM formulations. Ablations show that visual supervision from successful and failed continuations improves both prediction and control beyond action supervision alone. On four real-world tasks across Wuji and Sharpa, 3 x 3 grid evaluations show that two rounds of deployment learning increase success from 51.0% to 71.7% in cells with at least one initial success, a gain of 20.7 percentage points. These findings support continued predictive learning for improving control through deployment experience, making world modeling an active part of WAM adaptation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.37398 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.624Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).